English
Related papers

Related papers: Learning Syntax Without Planting Trees: Understand…

200 papers

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of…

Machine Learning · Computer Science 2025-06-11 Jerome Garnier-Brun , Marc Mézard , Emanuele Moscato , Luca Saglietti

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

Computation and Language · Computer Science 2020-10-13 Ethan Wilcox , Peng Qian , Richard Futrell , Ryosuke Kohita , Roger Levy , Miguel Ballesteros

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

We study whether a Large Language Model can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer is mapped into a rooted planar tree and the resulting sequence $…

Artificial Intelligence · Computer Science 2025-12-02 Alessandro Breccia , Federica Gerace , Marco Lippi , Gabriele Sicuro , Pierluigi Contucci

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…

Machine Learning · Computer Science 2026-05-01 Henrik Voigt , Michael Habeck , Joachim Giesen

We evaluate whether BERT, a widely used neural network for sentence processing, acquires an inductive bias towards forming structural generalizations through pretraining on raw data. We conduct four experiments testing its preference for…

Computation and Language · Computer Science 2020-09-25 Alex Warstadt , Samuel R. Bowman

Transformers have the capacity to act as supervised learning algorithms: by properly encoding a set of labeled training ("in-context") examples and an unlabeled test example into an input sequence of vectors of the same dimension, the…

Machine Learning · Computer Science 2024-12-16 Spencer Frei , Gal Vardi

While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking. Their capabilities have been probed on benchmarks which include a variety of structured and…

Machine Learning · Computer Science 2023-07-25 Yuchen Li , Yuanzhi Li , Andrej Risteski

Transformer models pre-trained with a masked-language-modeling objective (e.g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the…

Computation and Language · Computer Science 2021-12-17 Ian Porada , Alessandro Sordoni , Jackie Chi Kit Cheung

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random…

Machine Learning · Computer Science 2025-05-13 Francesco Cagnetta , Alessandro Favero , Antonio Sclocchi , Matthieu Wyart

Despite the success of language models using neural networks, it remains unclear to what extent neural models have the generalization ability to perform inferences. In this paper, we introduce a method for evaluating whether neural models…

Computation and Language · Computer Science 2020-05-05 Hitomi Yanaka , Koji Mineshima , Daisuke Bekki , Kentaro Inui

We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks…

Machine Learning · Computer Science 2025-05-27 Frank Cole , Yulong Lu , Wuzhe Xu , Tianhao Zhang

This study aims to understand how statistical biases affect the model's ability to generalize to in-distribution and out-of-distribution data on algorithmic tasks. Prior research indicates that transformers may inadvertently learn to rely…

Machine Learning · Computer Science 2024-09-11 John Mitros

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Computation and Language · Computer Science 2024-04-12 Jackson Petty , Sjoerd van Steenkiste , Ishita Dasgupta , Fei Sha , Dan Garrette , Tal Linzen

In the last half-decade, the field of natural language processing (NLP) has undergone two major transitions: the switch to neural networks as the primary modeling paradigm and the homogenization of the training regime (pre-train, then…

Computation and Language · Computer Science 2021-10-19 Artur Kulmizev , Joakim Nivre

We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization abilities on a…

Machine Learning · Computer Science 2020-10-22 Nicolas Gontier , Koustuv Sinha , Siva Reddy , Christopher Pal

Linguists have long held that a key aspect of natural language syntax is the recursive organization of language units into constituent structures, and research has suggested that current state-of-the-art language models lack an inherent…

Computation and Language · Computer Science 2024-11-27 Michael Ginn

We investigate the capabilities of transformer models on relational reasoning tasks. In these tasks, models are trained on a set of strings encoding abstract relations, and are then tested out-of-distribution on data that contains symbols…

Computation and Language · Computer Science 2024-04-17 Enric Boix-Adsera , Omid Saremi , Emmanuel Abbe , Samy Bengio , Etai Littwin , Joshua Susskind